Direct costs of severe hypoglycemia events in individuals with diabetes mellitus: a perspective from the Colombian health system - a single-center study / Michael Andrés García Rivera ; Natalia Andrea Rojas Henao ; Hernández Herrera, Ana C. ; Juliana Díaz Giraldo ; Carlos Esteban Builes Montaño  

Público ISBD Título : Direct costs of severe hypoglycemia events in individuals with diabetes mellitus: a perspective from the Colombian health system - a single-center study Tipo de documento : documento electrónico Autores : Michael Andrés García Rivera, Autor ; Natalia Andrea Rojas Henao, Autor ; Hernández Herrera, Ana C., Autor ; Juliana Díaz Giraldo, Autor ; Carlos Esteban Builes Montaño, Autor Fecha de publicación : 2025 Títulos uniformes : Hospital Practice Idioma : Inglés (eng) Palabras clave : Diabetes mellitus; Latin America; cost of illness; diabetes complications; hypoglycemia Resumen : Background and aims: Diabetes mellitus is one of the more prevalent chronic diseases globally, and healthcare expenditures for diabetes care are on the rise. Intensive diabetes treatment has been associated with reducing the risk of chronic complications. However, hypoglycemia, the most common adverse effect, poses a significant risk to individuals' lives and is linked to high costs for healthcare systems. Methods: We conducted a retrospective cross-sectional study to determine direct costs by identifying emergency room visits due to hypoglycemia events using diagnostic codes during January 2017 to June 2019. Direct costs were calculated using billed data from the payer and information on outpatient treatment regimens. Differences in median costs were estimated based on length of stay and type of outpatient treatment. Results: Data from 101 patients and the same number of events were included. Women represented (62.4%) of the patients, the median age was 70 (IQR 59.5-80). Blood glucose levels at admission ranged from 12 mg/dL to 67 mg/dL. Most patients were on insulin for outpatient treatment. The median cost of care per hypoglycemia episode was US $345.35 (IQR US $202-727.8), and the cost per episode was higher in patients treated with regimens that included sulfonylureas. Conclusions: The management of patients admitted to the emergency department with a diagnosis of hypoglycemia places a significant burden on the Colombian healthcare system, primarily due to the associated hospitalization costs. Patients treated with regimens that included sulfonylureas incurred higher costs per episode. Prevention, patient education, and individualized treatment approaches could help alleviate the burden of hypoglycemia on both patients and the healthcare system. Mención de responsabilidad : Rojas-Henao, Natalia A; Garcia-Rivera, Michael; Hernandez-Herrera, Ana C.; Díaz-Giraldo, Juliana; Builes-Montaño, Carlos E. Referencia : Hosp Pract (1995). 2025 Feb;53(1):2439775 DOI (Digital Object Identifier) : 10.1080/21548331.2024.2439775 PMID : 39648816 Derechos de uso : CC BY-NC-ND En línea : https://pubmed.ncbi.nlm.nih.gov/39648816/ Enlace permanente : https://hospitalpablotobon.cloudbiteca.com/pmb/opac_css/index.php?lvl=notice_dis Direct costs of severe hypoglycemia events in individuals with diabetes mellitus: a perspective from the Colombian health system - a single-center study [documento electrónico] / Michael Andrés García Rivera, Autor ; Natalia Andrea Rojas Henao, Autor ; Hernández Herrera, Ana C., Autor ; Juliana Díaz Giraldo, Autor ; Carlos Esteban Builes Montaño, Autor . - 2025. Obra : Hospital Practice Idioma : Inglés (eng) Palabras clave : Diabetes mellitus; Latin America; cost of illness; diabetes complications; hypoglycemia Resumen : Background and aims: Diabetes mellitus is one of the more prevalent chronic diseases globally, and healthcare expenditures for diabetes care are on the rise. Intensive diabetes treatment has been associated with reducing the risk of chronic complications. However, hypoglycemia, the most common adverse effect, poses a significant risk to individuals' lives and is linked to high costs for healthcare systems. Methods: We conducted a retrospective cross-sectional study to determine direct costs by identifying emergency room visits due to hypoglycemia events using diagnostic codes during January 2017 to June 2019. Direct costs were calculated using billed data from the payer and information on outpatient treatment regimens. Differences in median costs were estimated based on length of stay and type of outpatient treatment. Results: Data from 101 patients and the same number of events were included. Women represented (62.4%) of the patients, the median age was 70 (IQR 59.5-80). Blood glucose levels at admission ranged from 12 mg/dL to 67 mg/dL. Most patients were on insulin for outpatient treatment. The median cost of care per hypoglycemia episode was US $345.35 (IQR US $202-727.8), and the cost per episode was higher in patients treated with regimens that included sulfonylureas. Conclusions: The management of patients admitted to the emergency department with a diagnosis of hypoglycemia places a significant burden on the Colombian healthcare system, primarily due to the associated hospitalization costs. Patients treated with regimens that included sulfonylureas incurred higher costs per episode. Prevention, patient education, and individualized treatment approaches could help alleviate the burden of hypoglycemia on both patients and the healthcare system. Mención de responsabilidad : Rojas-Henao, Natalia A; Garcia-Rivera, Michael; Hernandez-Herrera, Ana C.; Díaz-Giraldo, Juliana; Builes-Montaño, Carlos E. Referencia : Hosp Pract (1995). 2025 Feb;53(1):2439775 DOI (Digital Object Identifier) : 10.1080/21548331.2024.2439775 PMID : 39648816 Derechos de uso : CC BY-NC-ND En línea : https://pubmed.ncbi.nlm.nih.gov/39648816/ Enlace permanente : https://hospitalpablotobon.cloudbiteca.com/pmb/opac_css/index.php?lvl=notice_dis

Reserva

Reservar este documento

Ejemplares(1)

Código de barras	Número de Ubicación	Tipo de medio	Ubicación	Sección	Estado
DD002357	AC-2025-040	Archivo digital	Producción Científica	Artículos científicos	Disponible

Natural Language Processing for Enhanced Clinical Decision Support in Allergy Verification for Medication Prescriptions / Juan Pablo Botero Aguirre ; Michael Andrés García Rivera  

Público ISBD Título : Natural Language Processing for Enhanced Clinical Decision Support in Allergy Verification for Medication Prescriptions Tipo de documento : documento electrónico Autores : Juan Pablo Botero Aguirre, Autor ; Michael Andrés García Rivera, Autor Fecha de publicación : 2025 Títulos uniformes : Mayo Clinic Proceedings: Digital Health Idioma : Inglés (eng) Idioma original : Inglés (eng) Resumen : Objective To develop and validate a named entity recognition (NER) model based on BERT-based model trained on Spanish-language corpor, for extracting allergy-related information from unstructured electronic health records Patients and Method The model was fine-tuned using 16,176 manually annotated allergy-related entities from anonimized patient records (hospitalized patients between January 1, 2021, and June 30, 2024). The data set was divided into training (80%) and testing (20%) subsets, and model performance was evaluated using accuracy, recall, and F1 score. The validated model was applied to another data set with 80,917 medication prescriptions from 5859 hospitalized patients with at least one prescribed medication (during August and September 2024) to detect potential prescription errors. Sensitivity, specificity, and Cohen ? were calculated using manual expert review as the gold standard Result The model achieved an accuracy of 87.28% and an F1 score of 0.80. It effectively identified medication names (F1=0.91) and adverse reactions (F1=0.85) but struggled with recommendation-related entities (F1=0.29). The model detected prescription errors in 0.96% of cases, with a sensitivity of 75.73% and specificity of 99.98%. The weighted ? score (0.7797) indicated substantial agreement with expert annotations Conclusion The BERT-based model trained on Spanish-language corpora–based NER model demonstrated strong performance in identifying nonallergic cases (specificity, 99.98%; negative predictive value, 99.97%) and showed promise for clinical decision support. Despite moderate sensitivity (75.73%), these results highlight the feasibility of using Spanish-language NER models to enhance medication safety. Mención de responsabilidad : Juan Pablo Botero Aguirre, Michael Andrés García Rivera Referencia : Mayo Clinic Proceedings: Digital Health Volume 3, Issue 3, September 2025, 100244 DOI (Digital Object Identifier) : 10.1016/j.mcpdig.2025.100244 Derechos de uso : CC BY-NC-ND En línea : https://www.sciencedirect.com/science/article/pii/S2949761225000513 Enlace permanente : https://hospitalpablotobon.cloudbiteca.com/pmb/opac_css/index.php?lvl=notice_dis Natural Language Processing for Enhanced Clinical Decision Support in Allergy Verification for Medication Prescriptions [documento electrónico] / Juan Pablo Botero Aguirre, Autor ; Michael Andrés García Rivera, Autor . - 2025. Obra : Mayo Clinic Proceedings: Digital Health Idioma : Inglés (eng) Idioma original : Inglés (eng) Resumen : Objective To develop and validate a named entity recognition (NER) model based on BERT-based model trained on Spanish-language corpor, for extracting allergy-related information from unstructured electronic health records Patients and Method The model was fine-tuned using 16,176 manually annotated allergy-related entities from anonimized patient records (hospitalized patients between January 1, 2021, and June 30, 2024). The data set was divided into training (80%) and testing (20%) subsets, and model performance was evaluated using accuracy, recall, and F1 score. The validated model was applied to another data set with 80,917 medication prescriptions from 5859 hospitalized patients with at least one prescribed medication (during August and September 2024) to detect potential prescription errors. Sensitivity, specificity, and Cohen ? were calculated using manual expert review as the gold standard Result The model achieved an accuracy of 87.28% and an F1 score of 0.80. It effectively identified medication names (F1=0.91) and adverse reactions (F1=0.85) but struggled with recommendation-related entities (F1=0.29). The model detected prescription errors in 0.96% of cases, with a sensitivity of 75.73% and specificity of 99.98%. The weighted ? score (0.7797) indicated substantial agreement with expert annotations Conclusion The BERT-based model trained on Spanish-language corpora–based NER model demonstrated strong performance in identifying nonallergic cases (specificity, 99.98%; negative predictive value, 99.97%) and showed promise for clinical decision support. Despite moderate sensitivity (75.73%), these results highlight the feasibility of using Spanish-language NER models to enhance medication safety. Mención de responsabilidad : Juan Pablo Botero Aguirre, Michael Andrés García Rivera Referencia : Mayo Clinic Proceedings: Digital Health Volume 3, Issue 3, September 2025, 100244 DOI (Digital Object Identifier) : 10.1016/j.mcpdig.2025.100244 Derechos de uso : CC BY-NC-ND En línea : https://www.sciencedirect.com/science/article/pii/S2949761225000513 Enlace permanente : https://hospitalpablotobon.cloudbiteca.com/pmb/opac_css/index.php?lvl=notice_dis

Reserva

Reservar este documento

Ejemplares(1)

Código de barras	Número de Ubicación	Tipo de medio	Ubicación	Sección	Estado
DD002381	AC-2025-064	Archivo digital	Producción Científica	Artículos científicos	Disponible

---

1 (1 - 2 / 2) Por página: 25 50 100 200